© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46074
    Prev
    Next
    INDEX
    Explanations

    contents of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    tg
    -0.09
    zie
    -0.09
    ulis
    -0.08
    builtin
    -0.08
    aws
    -0.08
    ford
    -0.08
    <section
    -0.08
    ody
    -0.08
    stuff
    -0.08
    pad
    -0.08
    POSITIVE LOGITS
     contents
    0.11
    OfFile
    0.11
     haz
    0.11
     Calvin
    0.10
    .rdf
    0.10
    /container
    0.10
     closets
    0.10
     Haz
    0.10
     proverb
    0.10
    sts
    0.10
    Activations Density 0.050%

    No Known Activations